本論文研究目的為建立非語言自然互動之意向估測模型，此模型將透過人類手部觸碰身體的位置座標估測蘊含的人類意向。基於人類的姿態動作改變初始的馬可夫意向機率，依此概念我們先後使用模糊馬可夫與時變模糊馬可夫機率模型，由於模糊馬可夫只適用於轉換與估測特定且具有規律的事件，其中只考慮現在與下一刻的狀態的機率。然而，人類的意向是一個時變的系統只能從人類的經驗或心理學統計資料分析概略的機率，為此我們提出時變模糊馬可夫模型估測人類的意向，此模組將透過人手與身體部位相互重疊時的座標作為輸入訊號，並經由模糊分析獲得相對應的模糊權重改變馬可夫機率，然後經由時變模組分析人手暫留於該部位的時間與整理環境的時間獲得時間機率權重，最後將模糊權重與時間機率權重相加總後調整人類的意向機率，如此一來將可獲知該部位所蘊含的非語言意向。
   依據上述方法我們獲得相同位置不同時間所產生的意向機率，此方法將使得人工智慧的決策機制更類似於人類的決策機制。於認知心理學中將人類的決策歸類區分為歸納推理與概率估算，而現今的人工智慧決策系統大部分使用歸納推理的方式獲得人類的資訊(例如：手勢辨識、智慧家庭控制等)。然而，我們所提出來的時變模糊馬可夫模型將運用歸納推理與概率估算人類的意向，如此一來將更類似人類的思考模式。若依此模組建構人類意向推論模型則必須要建構完整且合理的意向機率架構，所以本篇論文的意向辨識將與其它推論模型一樣侷限於初始意向機率模型或資料庫的大小。而本篇論文的意向辨識機率模型具備時變的特性所以更能模擬出類似人類的思考與決策模式，未來將再加以討論人類的自我學習機制，使意向辨識機率模型更加近似於人類的認知系統。

The estimation of human intention for robot decision mechanism is the ultimate goal of this thesis. The human decision mechanism most information to exist the non-verbal language in the human communication. If the human robot interaction via the human intention of non-verbal language estimation and analysis the information then the robot decision mechanism will be similarity the human thinking and reaction. Therefore, we propose time-varying fuzzy Markov model to estimate the human intention of meaning of posture. We will via MATLAB simulation the intention states of the hands touch body location purport the intention probability of behavior and emphasize the time-varying model into the intention inference system will be better then time-invariant inference system, because the human thinking will be varies with time. In this thesis, we establish a time-varying fuzzy Markov model to estimate human intention for natural non-verbal human robot interface. Based on human posture information, we change the probability between states to improve the accuracy of estimation of human intention. The advantages of the approach are three fold: i) non-verbal information is core of natural interaction; ii) time-varying probability improves estimation accuracy; and iii) fuzzy inference consider practical human experience.

Abstract in Chinese...................I
Abstract in English........................II
Contents.....................................III
List of Figures........................................V
List of Tables......................................VII
Chapter 1 Introduction.......1
1.1	Problem Statement…………………………………………………3
1.2	Objective of Research……………………………………………...4
1.3	Research Motivation……...………………………………………..4
1.4	Thesis Outline………………………………………...……………6
Chapter 2 Background………………...................7
2.1	Markov Chains……………………………………………………..7
2.2	Fuzzy Markov Model…………………………………………..….9
2.3	Time-varying Fuzzy Markov Model…………………………......10
Chapter 3	Methodology…………………………11
3.1	Initial Markov Probability Model………………………………...11
3.2	Fuzzy Markov Model…...….…………..……….……….……….14
3.3	Time-varying Fuzzy Markov Model….………………....……….18
3.3.1	Consider Waiting Time of Hands on the Body Location of Fuzzy Model…………………………………………………19
3.3.2	Time-varying Markov Model…………………………………20
Chapter 4 Simulation…………………………………………………… 22
4.1	Evaluation of Fuzzy Markov Model……………………………23
4.2	Evaluation of Time-varying Fuzzy Markov Model……25
4.3	Compare the Different Between Fuzzy Markov Model and Time-Varying Fuzzy Markov Model…………………………………35
Chapter 5 Conclusions……………………………………………………… 52
Reference……………………………………………………………………53
List of Figures...........................V
1.1	Non-verbal system concept map…………………..……………………...2
1.2	Human decision mechanism flow chart…………………………………..6
2.1	Markov probability model of the weather…………………………8
2.2	Definition the body range…………………………………...…………..10
3.1	Intention probability inference system flow chart……………12
3.2	Initial of intention Markov model……………………………………….13
3.3	Fuzzy Markov system flow chart………………………………………..15
3.4	Fuzzy Markov system concept map……………………………………..16
3.5	Define the head fuzzy membership method……………………………17
3.6	Time-varying fuzzy Markov system flow chart………………18
3.7	Hands on the body location of fuzzy membership map…………………19
4.1	The intention probability of hands on the body using fuzzy Markov model……………………………………………………………………24
4.2	Time-varying model flow chart…………………………………………26
4.3	The intention probability of hands on the head using time-varying fuzzy Markov model…………………………………………………………...27
4.4	The intention probability of hands on the head using time-varying fuzzy Markov model at the morning…………………………………………..28
4.5	The intention probability of hands on the head using time-varying fuzzy Markov model at the morning of working time………………………...29
4.6	The intention probability of hands on the head using time-varying fuzzy Markov model at the midday……………………………………………30
4.7	The intention probability of hands on the head using time-varying fuzzy Markov model at the night………………………………………………32
4.8	The intention probability of hands on the head using time-varying fuzzy Markov model at the midnight………………………………………….33
4.9	The intention probability of hands on the heart using fuzzy Markov model……………………………………………………………………38
4.10	The initial intention probability of hands on the heart using time-varying fuzzy Markov model………………………………………………….…39
4.11	The initial intention probability of hands on the heart using time-varying fuzzy Markov model at morning……………………………….……….40
4.12	The initial intention probability of hands on the heart using time-varying fuzzy Markov model at working time…………………………………..41
4.13	The initial intention probability of hands on the heart using time-varying fuzzy Markov model at midday…………………………………………42
4.14	The initial intention probability of hands on the heart using time-varying fuzzy Markov model at night……………………………………………43
4.15	The initial intention probability of hands on the heart using time-varying fuzzy Markov model at midnight……………………………………….45
List of Tables................................VII
2.1	The weather probability of tomorrow weather based on today weather…8
3.1	The initial Markov probability of next intention states based on current states…………………………………………………………………….14
3.2	The human head location of meaning of fuzzy rule…………………….17
4.1	The intention probability of hands on the head using time-varying fuzzy Markov model table……………………………………………………..36
4.2	Finally of intention probability table…………………………37
4.3	The intention inference simulation data using fuzzy Markov model of statistic table…………………………………………………………….46
4.4	The effectiveness of estimation the intention probability of conventional Markov model, context awareness inference model, fuzzy Markov model, and time-varying fuzzy Markov model…………………………………49
4.5	The intention inference simulation data using time-varying fuzzy Markov model of statistic table…………………………………………………..50
4.6	The intention probability data using time-varying fuzzy Markov model of statistic table…………………………………………………………….51

[1]	R. Krauss and S. Fussell, “Social psychological models of interpersonal communication,”Social psychology: Handbook of basic principles, pp. 655–701, 1996.
[2]	A. Mehrabian, Nonverbal communication. Aldine, 2007.
[3]	P. Joe Navarro, Marcin Karlins, What every body is saying: An Ex-FBI Agent’s Guide to Speed-Reading People, H. Publishers, Ed., 2009.
[4]	M. Gelfond and V. Lifschitz, “Action languages,” Electronic Transactions on AI, vol. 3, no. 16, 1998.
[5]	J.-C. Wang, H.-P. Lee, J.-F. Wang, and C.-B. Lin, “Robust environmental sound recognition for home automation,” Automation Science and Engineering, IEEE Transactions on, vol. 5, no. 1, pp. 25 –31, jan. 2008.
[6]	L.-P. Morency, “Modeling human communication dynamics [social sciences],” signal Processing Magazine, IEEE, vol. 27, no. 5, pp. 112 –116, sept. 2010.
[7]	K.-C. Kwak and S.-S. Kim, “Sound source localization with the aid of excitation source information in home robot environments,” Consumer Electronics, IEEE Transactions on, vol. 54, no. 2, pp. 852 –856, may 2008.
[8]	Y. Matsumoto, N. Sasao, T. Suenaga, and T. Ogasawara, “3d model-based 6-dof head tracking by a single camera for human-robot interaction,” in Robotics and Automation, 2009. ICRA ’09. IEEE International Conference on, may 2009, pp. 3194 –3199.
[9]	E. Yu and J. Aggarwal, “Human action recognition with extremities as semantic posture representation,” in Computer Vision and Pattern Recognition Workshops, 2009. CVPR Workshops 2009. IEEE Computer Society Conference on, june 2009, pp. 1 –8.
[10]	C.-F. Juang, C.-M. Chang, J.-R. Wu, and D. Lee, “Computer vision-based human body segmentation and posture estimation,” Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, vol. 39, no. 1, pp. 119 –133, jan. 2009.
[11]	A. Dey, “Understanding and using context,” Personal and ubiquitous computing, vol. 5, no. 1, pp. 4–7, 2001.
[12]	K. Oyama, H. Jaygarl, J. Xia, C. Chang, A. Takeuchi, and H. Fujimoto, “A human-machine dimensional inference ontology that weaves human intentions and requirement of context awareness systems,” in Computer Software and Applications, 2008. COMPSAC ’08. 32nd Annual IEEE International, 28 2008-aug. 1 2008, pp. 287 –294.
[13]	C. Chang, H. yi Jiang, H. Ming, and K. Oyama, “Situ: A situation-theoretic approach to context-aware service evolution,” Services Computing, IEEE Transactions on, vol. 2, no. 3, pp. 261 –275, july-sept. 2009.
[14]	K. Oyama, H. Jaygarl, J. Xia, C. Chang, A. Takeuchi, and H. Fujimoto, “Requirements analysis using feedback from context awareness systems,” in Computer Software and Applications, 2008. COMPSAC ’08. 32nd Annual IEEE International, 28 2008-aug. 1 2008, pp. 625 –630.
[15]	K. Oyama, A. Takeuchi, and H. Fujimoto, “Capis model based software design method for sharing experts’ thought processes,” in Computer Software and Applications Conference, 2006. COMPSAC ’06. 30th Annual International, vol. 1, sept. 2006, pp. 307 –316.
[16]	H. Ge and S. Asgarpoor, “Reliability evaluation of equipment and substations with fuzzy markov processes,” Power Systems, IEEE Transactions on, vol. 25, no. 3, pp. 1319 –1328, aug. 2010.
[17]	M.-Y. Hung, Introduction to Clinical Medicine. Farseeing Publishing Co., Ltd, 2009.
[18]	R. Bailey, A. Telephone, and N. Telegraph Company (New York, Human performance engineering: using human factors/ergonomics to achieve computer system usability. Prentice Hall Englewood Cliffs, NJ, 1989, vol. 1.
[19]	J. Rasmussen, “Skills, rules, and knowledge; signals, signs, and symbols, and other distinctions in human performance models.” IEEE TRANS. SYS. MAN CYBER., vol. 13, no. 3, pp. 257–266, 1983.
[20]	Z. Kowalczuk and M. Czubenko, “Model of human psychology for controlling autonomous robots,” in Methods and Models in Automation and Robotics (MMAR), 2010 15th International Conference on, aug. 2010, pp. 31 –36.
[21]	Y. Ho, T. Shibano, E. Sato-Shimokawara, and T. Yamaguchi, “The information providing system by using human motion recognition,” in Human System Interaction HSI), 2011 4th International Conference on, may 2011, pp. 110 –116.
[22]	Y. Ye, “Design and implementation of a real-time image processing based e-home robot,” 2003.
[23]	Y.-H. Chen, C.-H. Lu, K.-C. Hsu, L.-C. Fu, Y.-J. Yeh, and L.-C. Kuo, “Preference model assisted activity recognition learning in a smart home environment,” in Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on, oct. 2009, pp. 4657 –4662.
[24]	S. Koo and D.-S. Kwon, “Recognizing human intentional actions from the relative movements between human and robot,” in Robot and Human Interactive Communication, 2009. RO-MAN 2009. The 18th IEEE International Symposium on, 27, 2009-oct. 2 2009, pp. 939 –944.
[25]	J.-Y. Kuan, T.-H. Huang, and H.-P. Huang, “Human intention estimation method for a new compliant rehabilitation and assistive robot,” in SICE Annual Conference 2010, Proceedings of, aug. 2010, pp. 2348 –2353.
[26]	J.-H. Han and J.-H. Kim, “Human-robot interaction by reading human intention based on mirror-neuron system,” in Robotics and Biomimetics (ROBIO), 2010 IEEE International Conference on, dec. 2010, pp. 561 –566.
[27]	X. Zhang, B. Wang, X. Wang, T. Sugi, and M. Nakamura, “Human intention extracted from electromyography signals for tracking motion of meal assistance robot,” in Complex Medical Engineering, 2007. CME 2007. IEEE/ICME International Conference on, may 2007, pp. 1384 –1387.
[28]	D. Kahneman, “Attention and effort,” Englewood Cliffs: Prentice-Hall, 1973.
[29]	L. Rabiner, “A tutorial on hidden markov models and selected applications in speech recognition,” Proceedings of the IEEE, vol. 77, no. 2, pp. 257 –286, feb 1989.
[30]	D. Mohanta, P. Sadhu, and R. Chakrabarti, “Fuzzy markov model for determination of fuzzy state probabilities of generating units including the effect of maintenance scheduling,” Power Systems, IEEE Transactions on, vol. 20, no. 4, pp. 2117 – 2124, nov. 2005.
[31]	P. Cugnasca, M. De Andrade, and J. Camargo, J.B., “A fuzzy based approach for the design and evaluation of dependable systems using the markov model,” in Dependable Computing, 1999. Proceedings. 1999 Pacific Rim International Symposium on, 1999, pp. 112 –119.
[32]	O. Duque and D. Morinigo, “A fuzzy markov model including optimization techniques to reduce uncertainty,” in Electrotechnical Conference, 2004. MELECON 2004. Proceedings of the 12th IEEE Mediterranean, vol. 3, may 2004, pp. 841 – 844 Vol.3.
[33]	E. MacRae, “Estimation of time-varying markov processes with aggregate data,” Econometrica: journal of the Econometric Society, pp. 183–198, 1977.
[34]	M. M. K. S. c.-f. Maclin, Otto H., Cognitive Psychology 7th ed. Shanghai People’s Publishing House, 2008.